Relation Classification as Two-way Span-Prediction
arXiv:2010.04829
Abstract
The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as span-prediction (SP) problem, similar to Question answering (QA). We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. We demonstrate that the supervised SP objective works significantly better then the standard classification based objective. We achieve state-of-the-art results on the TACRED and SemEval task 8 datasets.
References in corpus (5)
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- The Natural Language Decathlon: Multitask Learning as Question Answering
- Downstream Model Design of Pre-trained Language Model for Relation Extraction Task
- Coreference Resolution as Query-based Span Prediction
- Generalizing Natural Language Analysis through Span-relation Representations